// https://syzkaller.appspot.com/bug?id=24c17416425edf118be6e3f39d34be912e037b14
// Copyright 2026 syzkaller project authors. All rights reserved.
// Use of this source code is governed by Apache 2 LICENSE that can be found in the LICENSE file.

// IMPORTANT: Do not copy the macros or definitions below directly into your reproducer.
// Instead, add the following line to your reproducer:
// #include "race_toolkit.h"

// --- Race Condition Toolkit ---
// Macros and snippets for CPU pinning, memory barriers, and userfaultfd.

#define _GNU_SOURCE
#include <errno.h>
#include <fcntl.h>
#include <linux/futex.h>
#include <linux/userfaultfd.h>
#include <poll.h>
#include <pthread.h>
#include <sched.h>
#include <stdint.h>
#include <stdio.h>
#include <stdlib.h>
#include <sys/ioctl.h>
#include <sys/syscall.h>
#include <time.h>
#include <unistd.h>

// Unbuffered I/O: Ensure logs are written immediately.
#define SETUP_UNBUFFERED_IO() setvbuf(stdout, NULL, _IONBF, 0)

// CPU Pinning: Pin the current thread to a specific CPU core.
#define PIN_TO_CPU(cpu)                                                \
	do {                                                           \
		cpu_set_t mask;                                        \
		CPU_ZERO(&mask);                                       \
		CPU_SET(cpu, &mask);                                   \
		if (sched_setaffinity(0, sizeof(mask), &mask) == -1) { \
			perror("sched_setaffinity");                   \
		}                                                      \
	} while (0)

// Memory Barrier: Ensure memory ordering.
#define MB() __atomic_thread_fence(__ATOMIC_SEQ_CST)

// Spin-wait Barrier: Wait until a memory location has a specific value.
// Best for tight race windows (low latency, no context switches).
#define WAIT_ON(addr, val)                                               \
	do {                                                             \
		while (__atomic_load_n(addr, __ATOMIC_ACQUIRE) != (val)) \
			;                                                \
	} while (0)

// Signal: Set a memory location to a specific value to release a WAIT_ON.
#define SIGNAL(addr, val) __atomic_store_n(addr, val, __ATOMIC_RELEASE)

// --- Timing Primitives ---
// Robust timing loops in VM environments (using CLOCK_MONOTONIC to avoid time(NULL) jumps).

static inline double timer_elapsed_sec(struct timespec* start)
{
	struct timespec now;
	if (clock_gettime(CLOCK_MONOTONIC, &now) == -1) {
		perror("clock_gettime(CLOCK_MONOTONIC) elapsed");
		exit(1);
	}
	return (double)(now.tv_sec - start->tv_sec) + (double)(now.tv_nsec - start->tv_nsec) / 1e9;
}

// Initialize a monotonic timer variable.
#define TIMER_START(t)                                          \
	struct timespec t;                                      \
	if (clock_gettime(CLOCK_MONOTONIC, &t) == -1) {         \
		perror("clock_gettime(CLOCK_MONOTONIC) start"); \
		exit(1);                                        \
	}

// Check if the elapsed time since 't' is less than 'sec' seconds.
#define TIMER_NOT_EXPIRED(t, sec) (timer_elapsed_sec(&(t)) < (double)(sec))

// Futex-based Event: Shared with syzkaller executor.
// Best for general synchronization or longer waits to save CPU.
typedef struct {
	int state;
} event_t;

static void event_init(event_t* ev)
{
	ev->state = 0;
}
static void event_reset(event_t* ev)
{
	ev->state = 0;
}

static void event_set(event_t* ev)
{
	if (__atomic_load_n(&ev->state, __ATOMIC_ACQUIRE)) {
		fprintf(stderr, "event already set\n");
		exit(1);
	}
	__atomic_store_n(&ev->state, 1, __ATOMIC_RELEASE);
	syscall(SYS_futex, &ev->state, FUTEX_WAKE | FUTEX_PRIVATE_FLAG, 1000000);
}

static void event_wait(event_t* ev)
{
	while (!__atomic_load_n(&ev->state, __ATOMIC_ACQUIRE))
		syscall(SYS_futex, &ev->state, FUTEX_WAIT | FUTEX_PRIVATE_FLAG, 0, 0);
}

// userfaultfd setup: Register a memory range for page fault handling.
static int setup_uffd(void* addr, size_t len)
{
	int uffd = syscall(__NR_userfaultfd, O_CLOEXEC | O_NONBLOCK);
	if (uffd == -1)
		return -1;
	struct uffdio_api api = {.api = UFFD_API, .features = 0};
	if (ioctl(uffd, UFFDIO_API, &api) == -1) {
		close(uffd);
		return -1;
	}
	struct uffdio_register reg = {
	    .range = {.start = (uintptr_t)addr, .len = len},
	    .mode = UFFDIO_REGISTER_MODE_MISSING};
	if (ioctl(uffd, UFFDIO_REGISTER, &reg) == -1) {
		close(uffd);
		return -1;
	}
	return uffd;
}

// --- Guidance on Usage ---
// 1. Use WAIT_ON/SIGNAL for tight race conditions to avoid scheduling overhead.
// 2. Use event_t (futexes) for general coordination or when waiting for longer periods.
// 3. Always use PIN_TO_CPU to increase race probability on multi-core systems.
// 4. Use setup_uffd to register a memory range for page fault handling. This allows you to
//    pause a thread accessing that memory until you handle the fault, creating a reliable
//    and controllable race window.
// 5. Call SETUP_UNBUFFERED_IO() at the start of main() to ensure that logs are printed
//    immediately. This is essential for understanding the exact interleaving of events
//    when debugging race conditions.
// 6. For timing-based loops (e.g., running a race for 10 seconds), do NOT use time(NULL)
//    or loops relying on real-time clocks, as VM clocks are highly unreliable and can fail or drift.
//    Instead, use the robust monotonic timing primitives TIMER_START and TIMER_NOT_EXPIRED:
//        TIMER_START(start);
//        while (TIMER_NOT_EXPIRED(start, 10.0)) {
//            // Your race logic here
//        }

#include <sys/ioctl.h>
#include <sys/stat.h>
#include <sys/types.h>
#include <fcntl.h>
#include <unistd.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <pthread.h>
#include <linux/loop.h>
#include <errno.h>

#ifndef BLKBSZSET
#define BLKBSZSET _IOW(0x12, 113, size_t)
#endif

int loop_fd = -1;
int dummy_fd = -1;
volatile int stop = 0;

void *thread1(void *arg) {
    PIN_TO_CPU(0);
    int bsz1 = 1024;
    int bsz2 = 4096;
    while (!__atomic_load_n(&stop, __ATOMIC_RELAXED)) {
        // Alternating block sizes forces kill_bdev() -> page_cache_delete_batch()
        ioctl(loop_fd, BLKBSZSET, &bsz1);
        ioctl(loop_fd, BLKBSZSET, &bsz2);
    }
    return NULL;
}

void *thread2(void *arg) {
    PIN_TO_CPU(1);
    char buf[4096] = {0};
    while (!__atomic_load_n(&stop, __ATOMIC_RELAXED)) {
        // Read 14 pages to fill the LRU batch (but not drain it)
        for (int i = 0; i < 14; i++) {
            ssize_t res = pread(loop_fd, buf, 4096, i * 4096);
            if (res < 0) {
                // Ignore errors here as loop device might be changing block size
                continue;
            }
        }
        
        // Spin a bit to widen the race window. This gives Thread 1 time to 
        // call kill_bdev and set folio->mapping = NULL for the pages in our batch.
        for (volatile int j = 0; j < 10000; j++) {}
        
        // Drain the LRU batch on CPU 1
        posix_fadvise(dummy_fd, 0, 4096, POSIX_FADV_DONTNEED);
    }
    return NULL;
}

int main() {
    SETUP_UNBUFFERED_IO();
    
    printf("[*] Setting up reproducer...\n");
    
    // Create a backing file for the loop device
    int fd = open("img", O_RDWR | O_CREAT | O_TRUNC, 0644);
    if (fd < 0) {
        printf("[-] Failed to open img: %s\n", strerror(errno));
        exit(1);
    }
    printf("[+] open img successful.\n");
    
    int res = ftruncate(fd, 1024 * 1024);
    if (res < 0) {
        printf("[-] Failed to ftruncate img: %s\n", strerror(errno));
        exit(1);
    }
    printf("[+] ftruncate img successful.\n");
    
    // Dummy fd used solely to trigger fadvise -> lru_add_drain
    dummy_fd = open("dummy", O_RDWR | O_CREAT | O_TRUNC, 0644);
    if (dummy_fd < 0) {
        printf("[-] Failed to open dummy: %s\n", strerror(errno));
        exit(1);
    }
    printf("[+] open dummy successful.\n");
    
    res = ftruncate(dummy_fd, 4096);
    if (res < 0) {
        printf("[-] Failed to ftruncate dummy: %s\n", strerror(errno));
        exit(1);
    }
    printf("[+] ftruncate dummy successful.\n");
    
    // Setup loop device
    int loop_ctl = open("/dev/loop-control", O_RDWR);
    if (loop_ctl < 0) {
        printf("[-] Failed to open /dev/loop-control: %s\n", strerror(errno));
        exit(1);
    }
    printf("[+] open /dev/loop-control successful.\n");
    
    int loop_num = ioctl(loop_ctl, LOOP_CTL_GET_FREE);
    if (loop_num < 0) {
        printf("[-] Failed to LOOP_CTL_GET_FREE: %s\n", strerror(errno));
        exit(1);
    }
    printf("[+] LOOP_CTL_GET_FREE successful, loop_num=%d.\n", loop_num);
    
    char loop_name[64];
    sprintf(loop_name, "/dev/loop%d", loop_num);
    
    loop_fd = open(loop_name, O_RDWR);
    if (loop_fd < 0) {
        printf("[-] Failed to open %s: %s\n", loop_name, strerror(errno));
        exit(1);
    }
    printf("[+] open %s successful.\n", loop_name);
    
    res = ioctl(loop_fd, LOOP_SET_FD, fd);
    if (res < 0) {
        printf("[-] Failed to LOOP_SET_FD: %s\n", strerror(errno));
        exit(1);
    }
    printf("[+] LOOP_SET_FD successful.\n");
    
    printf("[*] Starting race threads...\n");
    pthread_t t1, t2;
    res = pthread_create(&t1, NULL, thread1, NULL);
    if (res != 0) {
        printf("[-] Failed to pthread_create t1: %s\n", strerror(res));
        exit(1);
    }
    res = pthread_create(&t2, NULL, thread2, NULL);
    if (res != 0) {
        printf("[-] Failed to pthread_create t2: %s\n", strerror(res));
        exit(1);
    }
    printf("[+] Threads started successfully.\n");
    
    // Run the race for 5 seconds
    TIMER_START(start);
    while (TIMER_NOT_EXPIRED(start, 5.0)) {
        usleep(100000);
    }
    
    printf("[*] Stopping race threads...\n");
    __atomic_store_n(&stop, 1, __ATOMIC_RELAXED);
    pthread_join(t1, NULL);
    pthread_join(t2, NULL);
    printf("[+] Threads stopped successfully.\n");
    
    // Cleanup
    res = ioctl(loop_fd, LOOP_CLR_FD, 0);
    if (res < 0) {
        printf("[-] Failed to LOOP_CLR_FD: %s\n", strerror(errno));
    } else {
        printf("[+] LOOP_CLR_FD successful.\n");
    }
    
    close(loop_fd);
    close(loop_ctl);
    close(dummy_fd);
    close(fd);
    unlink("img");
    unlink("dummy");
    
    printf("[+] Cleanup successful.\n");
    return 0;
}